Role play-based question-answering by real users for building chatbots with consistent personalities

Ryuichiro Higashinaka, Masahiro Mizukami, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, Junji Tomita


Abstract
Having consistent personalities is important for chatbots if we want them to be believable. Typically, many question-answer pairs are prepared by hand for achieving consistent responses; however, the creation of such pairs is costly. In this study, our goal is to collect a large number of question-answer pairs for a particular character by using role play-based question-answering in which multiple users play the roles of certain characters and respond to questions by online users. Focusing on two famous characters, we conducted a large-scale experiment to collect question-answer pairs by using real users. We evaluated the effectiveness of role play-based question-answering and found that, by using our proposed method, the collected pairs lead to good-quality chatbots that exhibit consistent personalities.
Anthology ID:
W18-5031
Volume:
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venues:
SIGDIAL | WS
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
264–272
Language:
URL:
https://aclanthology.org/W18-5031
DOI:
10.18653/v1/W18-5031
Bibkey:
Cite (ACL):
Ryuichiro Higashinaka, Masahiro Mizukami, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, and Junji Tomita. 2018. Role play-based question-answering by real users for building chatbots with consistent personalities. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 264–272, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Role play-based question-answering by real users for building chatbots with consistent personalities (Higashinaka et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5031.pdf